Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/wcollins/packt-netops-ai-workshop/agents-mdgit clone --depth 1 https://github.com/wcollins/packt-netops-ai-workshopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/wcollins/packt-netops-ai-workshop/agents-md)<a href="https://agentmods.dev/instructions/wcollins/packt-netops-ai-workshop/agents-md"><img src="https://agentmods.dev/badge/instructions/wcollins/packt-netops-ai-workshop/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01070 | $0.01070 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade B, and why
packt-netops-ai-workshop AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo containerlab deploy -t topology.clab.yml # Deploy network How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
A three-part workshop teaching network engineers to leverage AI and LLMs for network automation. Built around Containerlab with Arista cEOS switches, Ansible automation, Model Context Protocol (MCP) servers, and Prometheus observability.
Commands
Environment Setup
uv sync # Install dependencies
./scripts/verify-setup.sh # Verify prerequisites
Lab 1 - Containerlab
cd lab-01-copilots
sudo containerlab deploy -t topology.clab.yml # Deploy network
sudo containerlab destroy -t topology.clab.yml # Teardown network
Lab 1 - Ansible
cd lab-01-copilots/ansible
source .venv/bin/activate
ansible-playbook playbooks/01-interfaces.yml -i inventories/clab.yml
ansible-playbook playbooks/04-set-interfaces.yml -i inventories/clab.yml \
--extra-vars "target_host=leaf1 interface_name=Ethernet3 description='New Link' ip_address=10.0.0.1/30"
Lab 2 - MCP Server
cd lab-02-mcp-server
mcp dev network_mcp_server.py # Test in MCP Inspector
mcp run network_mcp_server.py # Run for Claude Desktop
mcp run -t sse network_mcp_server.py # Run for remote access
Lab 3 - Observability Stack
cd lab-03-observability
docker compose up -d # Start Prometheus + Grafana
docker compose down # Stop stack
Testing & Quality
python -m pytest lab-02-mcp-server/tests/ -v # Run tests
ruff check . # Lint
mypy lab-02-mcp-server/ # Type check
Architecture
Network Topology
- Spines (2): spine1, spine2 - AS65100, IPs 198.18.1.11-12
- Leaves (4): leaf1-4 - AS65101-65104, IPs 198.18.1.21-24
- BGP spine-leaf fabric with point-to-point links
Lab Structure
Lab 1 (lab-01-copilots/): Ansible playbook development with Claude Code
ansible/playbooks/01-03.yml: Base configs for spine1 + leaf1ansible/playbooks/01.5-03.5.yml: Extended configs for remaining devicesansible/playbooks/04-09.yml: Single-operation playbooks for MCP integrationprompts/: Claude Code prompts for extending playbooks
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 121 lines · 1,070 tokens per session scan B e1347ce52fa2
packt-netops-ai-workshop AGENTS.md is an instructions file published in the GitHub repository wcollins/packt-netops-ai-workshop (29 stars, last pushed 6mo ago), licensed MIT. It adds 1,070 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
mazelingo CLAUDE.md
Instructions for Yeq6X/mazelingo, covering mazelingo, ビルド・開発, 構造 and ルール.
llm-ide-rules python-app.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering python app, factories and database & orm.
llm-ide-rules react.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering react, mock data, react hook form and styling.
rosetta republish-assets-not-npm.instructions.md
Instructions for tikoci/rosetta: The republishassets workflow input is for GitHub Release assets and OCI tags only.
feima-copilot-llms-extension copilot-instructions.md
Copilot instructions for feimacode/feima-copilot-llms-extension, covering feima copilot llms extension - copilot instructions, localization and 1. runtime strings — l10n/bundle.l10n.zh-cn.json.